Fuzzy Clustering-Based Filter

Luiz F.S. Coletta, Eduardo R. Hruschka, Thiago F. Covoes, Ricardo J.G.B. Campello

Publikation: Kapitel i bog/rapport/konference-proceedingKonferencebidrag i proceedingsForskningpeer review

Abstract

This paper introduces a filter, named FCF (Fuzzy Clustering-based Filter), for removing redundant features, thus making it possible to improve the efficacy and the efficiency of data mining algorithms. FCF is based on the fuzzy partitioning of features into clusters. The number of clusters is automatically estimated from data. After the clustering process, FCF selects a subset of features from the obtained clusters. To do so, we study four different strategies that are based on the information provided by the fuzzy partition matrix. We also show that these strategies can be combined for better performance. Empirical results illustrate the performance of FCF, which in general has obtained competitive results in classification tasks when compared to a related filter that is based on the hard partitioning of features.

OriginalsprogEngelsk
TitelInformation Processing and Management of Uncertainty in Knowledge-Based Systems Theory and Methods : 13th International Conference, IPMU 2010 Dortmund, Germny, June 28-July 2, 2010 Proceedings,ParT1
RedaktørerEyke Hullermeier, Rudolf Kruse, Frank Hoffmann
ForlagSpringer
Publikationsdato2010
Sider406-415
ISBN (Trykt)9783642140549
DOI
StatusUdgivet - 2010
Udgivet eksterntJa
BegivenhedInformation Processing and Management of Uncertainty in Knowledge-Based Systems: Theory and Methods, 13th International Conference, IPMU 2010, Proceedings - Dortmund, Tyskland
Varighed: 28. jun. 20102. jul. 2010

Konference

KonferenceInformation Processing and Management of Uncertainty in Knowledge-Based Systems: Theory and Methods, 13th International Conference, IPMU 2010, Proceedings
Land/OmrådeTyskland
ByDortmund
Periode28/06/201002/07/2010
NavnCommunications in Computer and Information Science
Vol/bind80 PART 1
ISSN1865-0929

Fingeraftryk

Dyk ned i forskningsemnerne om 'Fuzzy Clustering-Based Filter'. Sammen danner de et unikt fingeraftryk.

Citationsformater